CN109962956B - Method and system for recommending communication services to a user - Google Patents
Method and system for recommending communication services to a user Download PDFInfo
- Publication number
- CN109962956B CN109962956B CN201711428807.5A CN201711428807A CN109962956B CN 109962956 B CN109962956 B CN 109962956B CN 201711428807 A CN201711428807 A CN 201711428807A CN 109962956 B CN109962956 B CN 109962956B
- Authority
- CN
- China
- Prior art keywords
- user
- communication service
- service
- communication
- users
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q30/00—Commerce
- G06Q30/02—Marketing; Price estimation or determination; Fundraising
- G06Q30/0201—Market modelling; Market analysis; Collecting market data
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/51—Discovery or management thereof, e.g. service location protocol [SLP] or web services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/55—Push-based network services
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Accounting & Taxation (AREA)
- Development Economics (AREA)
- Finance (AREA)
- Strategic Management (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Telephonic Communication Services (AREA)
Abstract
The disclosure provides a method and a system for recommending communication services to a user, and relates to the technical field of data mining. The method comprises the following steps: determining each dimension of the communication service based on the existing communication service of the user; performing box separation processing on each dimension, and distributing the user to a corresponding feature group according to a box separation result; searching a similar group of the user based on the box separation result, calculating to obtain a communication service structure proportion of the similar group, and taking the communication service structure proportion as a recommendation probability; and selecting the communication service structure with the highest recommendation probability as a recommendation result from all the communication service structures to be recommended to the user, and recommending the communication service to the user. The method and the device can obviously reduce the calculated amount and improve the calculation efficiency and the practical effect on the premise of basically ensuring the recommendation accuracy.
Description
Technical Field
The present disclosure relates to the field of data mining technologies, and in particular, to a method and a system for recommending a communication service to a user.
Background
Collaborative filtering is a typical recommendation. The method mainly finds groups which are concerned with the interest of the user and have common experience through the self attribute of the user and past consumption records, and recommends the information of interest of the user according to the preference of similar groups. Individuals give a considerable degree of responses (such as scores) to the objects through a cooperative mechanism, and filtering purposes are achieved based on recording and calculation of the responses so as to help others to filter information and achieve personalized content recommendation.
The RFM (recent Frequency of consumption, consumption amount) technology is a common client grouping and value evaluation technology in client relationship management, and is commonly used to measure client value and client earning ability. The technology generally divides the customers into n groups by three dimensions of recent purchasing behavior, total frequency of purchasing and consumption amount of the customers, and the number and the content of the dimensions can be flexibly adjusted.
In theory, the scenario of asset recommendation for communication enterprise clients can be realized by a collaborative filtering technology. In the traditional collaborative filtering technology, a core service dimension is selected as a user 'preference' at first; then, calculating the similarity between every two users according to the dimension; then, analyzing a group with similarity higher than a certain threshold with the user as a learning object, and calculating recommendation probability of each asset structure (namely a communication service structure) through similarity weighting; and then recommending the communication service to the user according to the recommendation probability. Since the number of clients is usually huge (e.g., millions), direct use of the conventional collaborative filtering recommendation technique occupies extremely high computational resources (the similarity between all users needs to be calculated), so that the general computing environment is often unable to obtain effective results.
Disclosure of Invention
One technical problem that this disclosed embodiment solved is: a method or a system for recommending communication services to a user is provided, so that the calculation amount is reduced, and the calculation efficiency is improved.
According to an aspect of the embodiments of the present disclosure, there is provided a method for recommending a communication service to a user, including: determining each dimension of the communication service based on the existing communication service of the user; performing box separation processing on each dimension, and distributing the users to corresponding feature groups according to box separation results; searching a similar group of the user based on the box separation result, calculating to obtain a communication service structure proportion of the similar group, and taking the communication service structure proportion as a recommendation probability; and selecting the communication service structure with the highest recommendation probability as a recommendation result from all the communication service structures to be recommended to the user, and recommending the communication service to the user.
Optionally, the step of performing binning processing on each dimension, and allocating the user to a corresponding feature group according to a binning result includes: respectively allocating the users to corresponding box groups of all dimensions according to the data information of the users on all dimensions; and assigning the user into a respective feature group according to the features of the respective group of bins for each dimension to which the user is assigned.
Optionally, the step of finding similar groups of the users based on the binning results comprises: searching and obtaining other users which are consistent with the box separation results of the user in all dimensions, and taking all other users as similar groups of the user; wherein the similar groups are assigned to respective feature groups of the users.
Optionally, before calculating the communication traffic structure ratio, the method further includes: and judging whether the number of all users in the feature group is greater than or equal to a user number threshold value, if so, determining the feature group as an effective feature group, executing the step of calculating the communication service structure proportion, otherwise, determining the feature group as an ineffective feature group, and deleting the ineffective feature group.
Optionally, the step of calculating the communication service structure ratio of the similar group includes: and respectively calculating the proportion of the number of the users having each communication service structure in the similar group to the total number of the users of the similar group, and taking the proportion as the communication service structure proportion of the similar group.
Optionally, the step of calculating the communication service structure ratio of the similar group includes: under the condition that the user currently has a plurality of communication services, calculating the proportion of the communication service structures in the corresponding similar groups according to each communication service; and weighting the proportion of the same type of communication service structure in all similar groups, and calculating to obtain the weighted proportion of the communication service structure as the recommendation probability of the communication service structure.
Optionally, the method further comprises: setting a recommendation threshold according to a recommendation service requirement; the step of selecting the communication service structure with the highest recommendation probability as the recommendation result and recommending the communication service to the user comprises the following steps: and taking the communication service structure to be recommended with the recommendation probability greater than the recommendation threshold as a product package, comparing the product package with the existing communication services of the user, and selecting the communication service structure with the highest recommendation probability from the product package to recommend the communication services which are not available to the user currently to the user.
Optionally, the communication service includes: mobile services, broadband services or fixed line services.
Optionally, the communication service structure includes: single mobile service, single broadband service, single fixed telephone service, combined mobile and broadband service, combined mobile and fixed telephone service, combined broadband and fixed telephone service, or combined mobile, broadband and fixed telephone service.
Optionally, the dimensions of the mobile service include: at least one of call duration, GPRS traffic, short messenger usage, circle of communication size, network entry duration, equipment full-source income, quantity of mobile assets under the user name and quantity of postpaid assets under the user name.
Optionally, the dimension of the broadband service includes: at least one of the total number of internet surfing times, the number of internet surfing terminals, downlink bandwidth, internet access time, equipment all-source income, whether post-payment exists or not and whether a sales strategy exists or not.
Optionally, the dimension of the fixed line service includes: at least one of fixed-line calling duration, outgoing communication circle size, incoming communication circle size, network access duration and equipment full-source income.
According to another aspect of the embodiments of the present disclosure, there is provided a system for recommending a communication service to a user, including: the dimension acquisition unit is used for determining each dimension of the communication service based on the existing communication service of the user; the box separation processing unit is used for respectively carrying out box separation processing on each dimension and distributing the users to corresponding feature groups according to box separation results; the searching and calculating unit is used for searching a similar group of the user based on the box dividing result, calculating the communication service structure proportion of the similar group and taking the communication service structure proportion as a recommendation probability; and the service recommendation unit is used for selecting the communication service structure with the highest recommendation probability as a recommendation result from all the communication service structures to be recommended to the user and recommending the communication service to the user.
Optionally, the bin allocation processing unit is configured to allocate the user to a corresponding bin group of each dimension according to the data information of the user in each dimension, and allocate the user to a corresponding feature group according to the feature of the corresponding bin group of each dimension to which the user is allocated.
Optionally, the search calculation unit is configured to search for and obtain all other users that are consistent with the binning result of the user in each dimension, and use all the other users as a similar group of the users; wherein the similar groups are assigned to respective feature groups of the users.
Optionally, the search calculation unit is further configured to determine whether the number of all users in the feature group is greater than or equal to a user number threshold, if so, determine that the feature group is an effective feature group, calculate the communication service structure ratio, otherwise, determine that the feature group is an ineffective feature group, and delete the ineffective feature group.
Optionally, the search calculation unit is configured to calculate a ratio of the number of users having each communication service structure in the similar group to a total number of users of the similar group, as a communication service structure ratio of the similar group.
Optionally, the search calculation unit is configured to, under the condition that the user currently has multiple communication services, calculate a ratio of communication service structures in corresponding similar groups according to each communication service, perform weighting processing on the ratios of the same type of communication service structures in all similar groups, and calculate a weighted ratio of the communication service structure as a recommendation probability of the communication service structure.
Optionally, the service recommending unit is configured to set a recommendation threshold according to a recommendation service requirement, use a communication service structure to be recommended, of which the recommendation probability is greater than the recommendation threshold, as a product package, compare the product package with an existing communication service of the user, and select a communication service structure with the highest recommendation probability from the product package to recommend, to the user, a communication service that the user does not currently have.
Optionally, the communication service includes: mobile services, broadband services or fixed line services.
Optionally, the communication service structure includes: single mobile service, single broadband service, single fixed telephone service, combined mobile and broadband service, combined mobile and fixed telephone service, combined broadband and fixed telephone service, or combined mobile, broadband and fixed telephone service.
Optionally, the dimensions of the mobile service include: at least one of call duration, GPRS traffic, short messenger usage, circle of communication size, network entry duration, equipment full-source income, quantity of mobile assets under the user name and quantity of postpaid assets under the user name.
Optionally, the dimension of the broadband service includes: at least one of the total number of internet surfing times, the number of internet surfing terminals, downlink bandwidth, internet access time, equipment all-source income, whether post-payment exists or not and whether a sales strategy exists or not.
Optionally, the dimension of the fixed line service includes: at least one of fixed-line calling duration, outgoing communication circle size, incoming communication circle size, network access duration and equipment full-source income.
According to another aspect of the embodiments of the present disclosure, there is provided a system for recommending a communication service to a user, including: a memory; and a processor coupled to the memory, the processor configured to perform the method as previously described based on instructions stored in the memory.
According to another aspect of embodiments of the present disclosure, there is provided a computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the method as previously described.
In the method or system of the above embodiment, each dimension of the communication service may be determined based on the existing communication service of the user; performing box separation processing on each dimension, and distributing the user to a corresponding feature group according to a box separation result; searching a similar group of the user based on the box separation result, calculating to obtain a communication service structure proportion of the similar group, and taking the communication service structure proportion as a recommendation probability; and selecting the communication service structure with the highest recommendation probability as a recommendation result from all the communication service structures to be recommended to the user, and recommending the communication service to the user. The method or the system can obviously reduce the calculated amount and improve the calculation efficiency and the practical effect on the premise of basically ensuring the recommendation accuracy.
Other features of the present disclosure and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure may be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:
FIG. 1 is a flow diagram illustrating a method for recommending communication services to a user in accordance with some embodiments of the present disclosure;
FIG. 2 is a flow diagram illustrating a method for recommending communication services to a user according to further embodiments of the present disclosure;
FIG. 3 is a block diagram that schematically illustrates a system for recommending communication services to a user, in accordance with some embodiments of the present disclosure;
FIG. 4 is a block diagram that schematically illustrates a system for recommending communication services to a user, in accordance with further embodiments of the present disclosure;
fig. 5 is a block diagram that schematically illustrates a system for recommending communication services to a user, in accordance with further embodiments of the present disclosure.
Detailed Description
Various exemplary embodiments of the present disclosure will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
Fig. 1 is a flow diagram illustrating a method for recommending communication services to a user, according to some embodiments of the present disclosure.
In step S102, the dimensions of the communication service are determined based on the existing communication service of the user.
In some embodiments, the communication traffic may include: mobile services, broadband services or fixed line services.
In some embodiments, the dimensions of the mobile service may include: at least one of a call duration, a General Packet Radio Service (GPRS) traffic, a short messenger usage, a circle of communication size, a network access duration, a device full-source income, a number of mobile assets under a user name, and a number of postpaid assets under the user name.
In some embodiments, the dimensions of the broadband service may include: at least one of the total number of internet surfing times, the number of internet surfing terminals, downlink bandwidth, internet access time, equipment full-source income, whether post-payment exists or not and whether a sales strategy exists or not.
In some embodiments, the dimensions of the fixed line service may include: at least one of fixed-line calling duration, outgoing communication circle size, incoming communication circle size, network access duration and equipment full-source income.
In step S102, the dimensions of a communication service may be determined based on the fact that the user already has the communication service. For example, the respective dimensions of the mobile service (or broadband service or fixed line service) may be determined based on the mobile service (or broadband service or fixed line service) that the user already has.
It should be noted that although the communication service listed above may include a mobile service, a broadband service or a fixed telephone service, it should be understood by those skilled in the art that the communication service may also include other services besides the above three services, for example, IPTV (Internet Protocol Television) service may also be included, for example, the dimension of the IPTV service may include at least one of the number of times of turning on the IPTV and the cost of consuming the IPTV, and therefore the scope of the disclosure is not limited thereto.
In step S104, the dimensions are subjected to binning processing, and the users are assigned to the corresponding feature groups according to the binning result.
In some embodiments, this step S104 may include: according to the data information of the user in each dimension, the user is respectively allocated to the corresponding box group of each dimension; and assigning the user to the respective feature group according to the features of the respective group of bins for each dimension to which the user is assigned. Here, the features of the feature group are composed of the features of the respective tank group.
The following description takes the existing mobile service of the user a as an example:
suppose that the mobile service of the user a has two dimensions, which are the call duration and the GPRS traffic, for example, the call duration is 300min, and the GPRS traffic is 2G.
On one hand, when the call duration is subjected to the binning processing, for example, the call duration may be divided into 3 bin groups, which are as follows:
calling time box group 1: the call duration is more than 500min, and users in the call duration box group 1 can be considered to have more call durations;
calling time box group 2: the call duration is more than or equal to 100min and less than or equal to 500min, and the users in the call duration box group 2 can be considered to have medium call duration;
calling time box group 3: the call duration is less than 100min, and it can be considered that the users in the call duration box group 3 have less call durations.
Since the call duration of the user a is 300min, the user a is allocated to the call duration box group 2 in the dimension of the call duration.
On the other hand, when performing the binning processing on the GPRS traffic, for example, the GPRS traffic may be divided into 3 bin groups, which are as follows:
flow box group 1: the GPRS traffic is greater than 10G, and it can be considered that users in the traffic box group 1 have more GPRS traffic;
the flow box group 2: the GPRS flow is more than or equal to 5G and less than or equal to 10G, and users in the flow box group 2 can be considered to have medium GPRS flow;
flow box group 3: GPRS traffic <5G, it can be considered that the users in this traffic box group 3 have relatively less GPRS traffic.
Since the GPRS traffic of subscriber a is 2G, subscriber a is allocated to traffic box group 3 in the dimension of the GPRS traffic.
Furthermore, since the call duration has 3 boxes and the GPRS traffic has 3 boxes, it can be determined that the feature group consisting of the call duration and the GPRS traffic has 3 × 3 ═ 9, respectively as follows:
characteristic group 1: the call duration is more than 500min, and the GPRS flow is more than 10G, namely the call duration is more and the GPRS flow is more;
feature group 2: the call duration is more than 500min, and the GPRS flow is less than or equal to 10G and is less than or equal to 5G, namely the call duration is more and the GPRS flow is medium;
feature group 3: the call duration is more than 500min, and the GPRS flow is less than 5G, namely the call duration is more and the GPRS flow is less;
feature group 4: the call duration is more than or equal to 100min and less than or equal to 500min, and the GPRS flow is greater than 10G, namely the call duration is medium and the GPRS flow is more;
feature group 5: the call duration is more than or equal to 100min and less than or equal to 500min, and the GPRS flow is more than or equal to 5G and less than or equal to 10G, namely the call duration is medium and the GPRS flow is medium;
feature group 6: the call duration is more than or equal to 100min and less than or equal to 500min, and the GPRS flow is less than 5G, namely the call duration is medium and the GPRS flow is less;
feature group 7: the call duration is less than 100min, and the GPRS flow is greater than 10G, namely the call duration is less and the GPRS flow is more;
feature group 8: the call duration is less than 100min, and the GPRS flow is less than or equal to 5G and less than or equal to 10G, namely the call duration is less and the GPRS flow is medium;
feature group 9: the call duration is less than 100min, and the GPRS traffic is less than 5G, i.e., the call duration is less and the GPRS traffic is less.
Depending on the characteristics of the subscriber a being assigned to the talk length box group 2 and the traffic box group 3, the subscriber a is assigned to the characteristic group 6.
In some embodiments, a plurality of users included in the user group may be subjected to binning, which is similar to the quantile concept, namely: the data is divided into N equally sized portions based on the bin target, e.g., the data may be sorted first from small to large and then the data within each bin group is allocated evenly.
In step S106, a similar group of users is searched based on the binning result, a communication service structure ratio of the similar group is calculated, and the communication service structure ratio is used as a recommendation probability (or referred to as an acceptance probability).
In some embodiments, the step of finding similar groups of users based on the binned results may comprise: searching and obtaining other users which are consistent with the box separation result of the user in each dimension, and taking all other users as similar groups of the user; wherein the similar groups are assigned to the respective feature groups of the user.
For example, the user a has the characteristics of medium call duration and less GPRS traffic, and other users having the characteristics of medium call duration and less GPRS traffic can be searched among all users, and the searched users form a similar group of the user a. For example, 100 users are found to have the above characteristics, then the 100 users constitute the similar group of the user a. In fact, the similar group is all other users that fit the features of the feature group (e.g., feature group 6) in which user a is located.
In some embodiments, a communication service structure (alternatively referred to as an asset structure) may include: single mobile service, single broadband service, single fixed telephone service, combined mobile and broadband service, combined mobile and fixed telephone service, combined broadband and fixed telephone service, or combined mobile, broadband and fixed telephone service.
In some embodiments, the step of calculating the proportion of the communication service structures of the similar groups may include: and respectively calculating the proportion of the number of the users having each communication service structure in the similar group to the total number of the users of the similar group, and taking the proportion as the communication service structure proportion of the similar group.
For example, in the above-mentioned similar group consisting of 100 found users, 30 users are single mobile services, 35 users are combined mobile and broadband services, 15 users are combined mobile and fixed telephone services, and 20 users are combined mobile, broadband and fixed telephone services, and the ratio of each communication service structure is shown in table 1.
Table 1 exemplary communication traffic structure ratios of similar groups
| Communication service architecture | Ratio of |
| Single mobile service | 30％ |
| Mobile and broadband combined services | 35％ |
| Combined mobile and fixed telephone service | 15％ |
| Combined mobile, broadband and fixed telephone service | 20％ |
As can be seen from table 1, the recommendation probability of the single mobile service is 30%, the recommendation probability of the mobile and broadband combined service is 35%, the recommendation probability of the mobile and fixed telephone combined service is 15%, and the recommendation probability of the mobile, broadband and fixed telephone combined service is 20%.
In some embodiments, before calculating the traffic structure proportion, the method may further comprise: and judging whether the number of all users in the feature group is greater than or equal to a user number threshold value, if so, determining that the feature group is a valid feature group (namely, the number of users of the similar group in the feature group is valid), executing the step of calculating the communication service structure proportion, otherwise, determining that the feature group is an invalid feature group (namely, the number of users of the similar group in the feature group is invalid), and deleting the invalid feature group.
Here, the threshold of the number of users in the feature group is set to eliminate the influence of the abnormal value on the calculation result. For example, if only 5 users having features with medium call duration and less GPRS traffic are found in the above search process, the 5 users form a similar group of the user a, and if the threshold of the number of users in the feature group 6 is 10, the similar group of the user a has only 5 users, so that the feature group 6 is an invalid feature group, and thus the influence of the abnormal value on the service on the calculation result can be eliminated. It should be noted that the threshold number of users for each feature group may be set as needed.
In step S108, the communication service structure with the highest recommendation probability is selected as the recommendation result from all the communication service structures to be recommended to the user, and the communication service is recommended to the user.
In some embodiments, the communication service structure to be recommended may be a communication service structure more than the communication services already existing for the user. For example, if the existing communication service structure of the user a is a single mobile service, when recommending a service to the user a, a mobile and broadband combined service, a mobile and fixed phone combined service, or a mobile, broadband and fixed phone combined service is recommended to the user a, and a single mobile service is no longer recommended to the user a, so that the communication service of the user a can be increased.
For example, in all the communication service structures to be recommended to the user a, the recommendation probability of the mobile and broadband combination service is 35%, which is the highest recommendation probability, and therefore, the mobile and broadband combination service is selected as the recommendation result, and the communication service, for example, the broadband service is recommended to the user.
In some embodiments, the method may further comprise: and setting a recommendation threshold according to the recommendation service requirement. The recommendation threshold may be a threshold that is commonly employed by multiple users. The step 108 may include: and taking the communication service structure to be recommended with the recommendation probability larger than the recommendation threshold as a product package, comparing the product package with the existing communication service of the user, and selecting the communication service structure with the highest recommendation probability from the product package to recommend the communication service which does not exist in the user currently to the user. If the recommendation probability of the communication service structure to be recommended does not exceed (is less than or equal to) the recommendation threshold, the communication service may not be recommended to the user. The recommendation threshold may function as a recommendation trigger.
For example, the recommendation threshold may be set to 0.16, and as can be seen from the above embodiments, in the similar group of the user a, the recommendation probability of the mobile and broadband combined service is 35%, and the recommendation probability of the mobile, broadband, and fixed-line combined service is 20%, which are both greater than the recommendation threshold, these two communication service structures to be recommended are taken as product packages, and compared with the existing communication service of the user a, and the mobile and broadband combined service structure with the highest recommendation probability is selected from the product packages to recommend, to the user, a communication service that the user does not currently have, for example, a broadband service.
To this end, a method for recommending communication services to a user according to some embodiments of the present disclosure is provided. In the method, each dimension of the communication service can be determined based on the existing communication service of the user; performing box separation processing on each dimension, and distributing the user to a corresponding feature group according to a box separation result; searching a similar group of the user based on the box separation result, calculating to obtain a communication service structure proportion of the similar group, and taking the communication service structure proportion as a recommendation probability; and selecting the communication service structure with the highest recommendation probability as a recommendation result from all the communication service structures to be recommended to the user, and recommending the communication service to the user. The method disclosed by the embodiment of the invention can obviously reduce the calculated amount and improve the calculation efficiency and the practical effect on the premise of basically ensuring the recommendation accuracy.
In the method of the embodiment of the disclosure, based on collaborative filtering and RFM ideas, core dimensions of communication service structure states, usage behaviors, income contributions and the like of communication users to basic services (such as mobile, broadband, fixed line and IPTV) are used as product preferences of the users, a binning technique is used to change a user similarity evaluation mode, communication service structure conditions of similar groups are calculated for each user, recommendation probability is calculated, and whether an asset recommendation opportunity exists is judged, so that an asset combination of broadband, mobile or fixed line can be accurately recommended for the users.
In some embodiments, the step of calculating the proportion of the communication service structures of the similar groups may include: under the condition that a user currently has a plurality of communication services, calculating the proportion of the communication service structures in the corresponding similar groups according to each communication service; and weighting the proportion of the same type of communication service structure in all similar groups, and calculating to obtain the weighted proportion of the communication service structure as the recommendation probability of the communication service structure.
For example, if the user B has two services, namely, broadband and fixed-line, the user B is subjected to binning processing for each dimension of the broadband, and is allocated to a first feature group related to the broadband according to the binning result, and is subjected to binning processing for each dimension of the fixed-line, and is allocated to a second feature group related to the fixed-line according to the binning result.
Then, the first similar group of the user B in the broadband aspect and the second similar group of the user B in the fixed telephone aspect are respectively searched. For example, a user in the first similar group may have four communication service structures, such as a single broadband service, a combined mobile and broadband service, a combined broadband and fixed-line service, and a combined mobile, broadband, and fixed-line service, and the ratios of these communication service structures are calculated respectively, and the ratios of these three communication service structures, such as a single mobile service, a single fixed-line service, a combined mobile and fixed-line service, that are not included in the first similar group, may be considered as 0 respectively. The users in the second similar group can have four communication service structures of single fixed telephone service, mobile and fixed telephone combined service, broadband and fixed telephone combined service, mobile, broadband and fixed telephone combined service and the like, and respectively calculate the proportion of the communication service structures, and the proportion of the three communication service structures of single mobile service, single broadband service, mobile and broadband combined service and the like which are not in the second similar group can be respectively considered as 0.
Then, the proportion of the same communication service structure in the first similar group and the second similar group is weighted, and the weighted proportion of the communication service structure is calculated. For example, the formula for calculating the weighted ratio of mobile and broadband combined services is as follows:
the ratio of the mobile and broadband combined traffic in the first similar group × weight 1+ the ratio of the mobile and broadband combined traffic in the second similar group (the ratio is 0) × weight 2 is the weighted ratio of the mobile and broadband combined traffic. Here, the weight may be set according to actual needs. The calculation formulas of other communication service structures are similar and are not described in detail here. Through the above steps, the weighting ratio of each communication service structure is calculated and taken as the recommendation probability of the communication service structure.
Fig. 2 is a flow diagram illustrating methods for recommending communication services to a user according to further embodiments of the present disclosure.
In step S202, the dimensions of the communication service are determined based on the existing communication service of the user.
In step S204, the user is respectively allocated to the corresponding box groups of each dimension according to the data information of the user in each dimension.
In step S206, the user is assigned to a respective feature group according to the features of the respective group of boxes for each dimension to which the user is assigned.
In step S208, all other users consistent with the binning result of the user in each dimension are searched and obtained, and the other users are taken as a similar group of the user, and the similar group is assigned to the corresponding feature group of the user.
In step S210, it is determined whether the number of all users in the feature group is greater than or equal to a user number threshold. If so, the process proceeds to step S212, otherwise, the process proceeds to step S214.
In step S212, the feature group is determined to be an effective feature group, the communication service structure ratio of the similar group is calculated, and the communication service structure ratio is used as the recommendation probability.
For example, summarizing the communication service structure of the users in each effective feature group (the number of users in the feature group is higher than the threshold number of users to basically ensure the universality and the effectiveness of the recommendation), and calculating the ranking and the proportion of the communication service structure of the users in the feature group as the recommended communication service structure and the recommendation probability of each user on the communication service category. For example: at present, a certain user in a project comprises three assets of mobile, fixed line and broadband, then a communication service structure and recommendation probability in the same sub-box are respectively calculated according to the three asset sub-box results, and finally the communication service structure and the recommendation probability are weighted.
In step S214, the feature group is determined to be an invalid feature group, and the invalid feature group is deleted.
In step S216, the communication service structure with the highest recommendation probability is selected as the recommendation result from all the communication service structures to be recommended to the user, and the communication service is recommended to the user.
In the method of the above embodiment, the method can segment the massive communication user group into a plurality of feature groups by performing binning processing on each dimension, which can greatly reduce the overall calculation pressure and hardly lose the user information amount. The box separation processing can convert the existing correlation calculation between continuous variables into the classified variable statistical calculation, so that compared with the existing user-based collaborative filtering technology, the method greatly improves the calculation efficiency and the practical effect on the premise of basically ensuring the recommendation accuracy. Moreover, the method provides more opportunities for self-defining adjustment of the granularity (the granularity mainly refers to the number of the boxes when the user similarity is classified) and the threshold, and the flexibility and the service applicability of the scheme are obviously improved.
In the method of the embodiment of the disclosure, a characteristic group where a single user is located is positioned according to the core service dimension of the single user; calculating the recommendation probability of each communication service (such as mobile, broadband or fixed line) in the located feature group; flexibly determining a recommendation threshold according to the service requirement; and taking all the communication service structures with the calculated recommendation probability larger than the recommendation threshold value as a product package, comparing the product package with the existing service of the user, recommending and filling the service which does not exist at present of the user, and finishing the personalized accurate recommendation.
Fig. 3 is a block diagram that schematically illustrates a system for recommending communication services to a user, in accordance with some embodiments of the present disclosure. As shown in fig. 3, the system may include: the system comprises a dimension acquisition unit 302, a binning processing unit 304, a search calculation unit 306 and a service recommendation unit 308.
The dimension obtaining unit 302 may be configured to determine each dimension of the communication service based on the existing communication service of the user.
The binning processing unit 304 may be configured to perform binning processing on each dimension, and assign the user to a corresponding feature group according to a binning result.
The search calculation unit 306 may be configured to search for a similar group of the user based on the binning result, calculate a communication service structure ratio of the similar group, and use the communication service structure ratio as the recommendation probability.
The service recommendation unit 308 may be configured to select, as a recommendation result, a communication service structure with the highest recommendation probability from all communication service structures to be recommended to the user, and recommend the communication service to the user.
In the system of the above embodiment, the dimension acquiring unit determines each dimension of the communication service based on the existing communication service of the user; the box separation processing unit is used for respectively carrying out box separation processing on each dimension and distributing the user to a corresponding feature group according to a box separation result; the searching and calculating unit searches a similar group of the user based on the box dividing result, calculates the communication service structure proportion of the similar group, and takes the communication service structure proportion as the recommendation probability; and the service recommending unit selects the communication service structure with the highest recommending probability as a recommending result in all the communication service structures to be recommended to the user, and recommends the communication service to the user. The system provided by the embodiment of the disclosure can obviously reduce the calculated amount on the premise of basically ensuring the recommendation accuracy, and greatly improves the calculation efficiency and the practical effect.
In some embodiments, the communication traffic may include: mobile services, broadband services or fixed line services.
In some embodiments, the communication traffic structure may include: single mobile service, single broadband service, single fixed telephone service, combined mobile and broadband service, combined mobile and fixed telephone service, combined broadband and fixed telephone service, or combined mobile, broadband and fixed telephone service.
In some embodiments, the dimensions of the mobile service may include: at least one of call duration, GPRS traffic, short messenger usage, circle of communication size, network entry duration, equipment full-source income, quantity of mobile assets under the user name and quantity of postpaid assets under the user name.
In some embodiments, the dimensions of the broadband service may include: at least one of the total number of internet surfing times, the number of internet surfing terminals, downlink bandwidth, internet access time, equipment all-source income, whether post-payment exists or not and whether a sales strategy exists or not.
In some embodiments, the dimension of the fixed line service may include: at least one of fixed-line calling duration, outgoing communication circle size, incoming communication circle size, network access duration and equipment full-source income.
In some embodiments of the present disclosure, the binning processing unit 304 may be configured to assign a user to respective bin groups of respective dimensions according to data information of the user in the respective dimensions, and to assign the user to a respective feature group according to a feature of the respective bin group of the respective dimension to which the user is assigned.
In some embodiments of the present disclosure, the search calculation unit 306 may be configured to search for and obtain all other users that are consistent with the binning result of the user in each dimension, and use all other users as a similar group of the user; wherein the similar groups are assigned to the respective feature groups of the user.
In some embodiments of the present disclosure, the search calculation unit 306 may be further configured to determine whether the number of all users in the feature group is greater than or equal to a user number threshold, if so, determine that the feature group is a valid feature group, calculate the communication service structure ratio, otherwise, determine that the feature group is an invalid feature group, and delete the invalid feature group.
In some embodiments of the present disclosure, the search calculation unit 306 may be configured to calculate a ratio of the number of users having each communication service structure in the similar group to the total number of users of the similar group as a communication service structure ratio of the similar group.
In some embodiments of the present disclosure, the search calculation unit 306 may be configured to, under the condition that the user currently has multiple communication services, calculate, according to each communication service, a ratio of a communication service structure in a corresponding similar group, perform weighting processing on the ratios of the same type of communication service structures in all similar groups, and calculate a weighted ratio of the type of communication service structure as a recommendation probability of the type of communication service structure.
In some embodiments of the present disclosure, the service recommending unit 308 may be configured to set a recommendation threshold according to a recommendation service requirement, use a communication service structure to be recommended whose recommendation probability is greater than the recommendation threshold as a product package, compare the product package with an existing communication service of the user, and select a communication service structure with a highest recommendation probability in the product package to recommend, to the user, a communication service that the user does not currently have.
Compared with the prior art, the method or the system of the embodiment of the disclosure has the following advantages:
(1) according to the method or the system, through fusion of RFM technical ideas, compared with the existing collaborative filtering technology based on the user, on the premise that recommendation accuracy is basically guaranteed, the calculation efficiency and the practical effect are greatly improved.
(2) The method or the system disclosed by the embodiment of the invention subdivides the users into the respective feature groups by carrying out the box separation treatment on the core dimension, and limits the number of the users in the minimum effective feature group, so that the recommended result has stronger practicability compared with the prior recommendation technology.
(3) The method or the system disclosed by the embodiment of the invention supports custom adjustment of the client partition granularity and the recommendation threshold, and has stronger flexibility and service applicability compared with the prior recommendation technology.
Fig. 4 is a block diagram that schematically illustrates a system for recommending communication services to a user, in accordance with further embodiments of the present disclosure. The system includes a memory 410 and a processor 420. Wherein:
the memory 410 may be a magnetic disk, flash memory, or any other non-volatile storage medium. The memory is used for storing instructions in the embodiments corresponding to fig. 1 and/or fig. 2.
In one embodiment, as also shown in FIG. 5, the system 500 includes a memory 510 and a processor 520. Processor 520 is coupled to memory 510 by a BUS 530. The system 500 may also be coupled to an external storage device 550 via a storage interface 540 for facilitating retrieval of external data, and may also be coupled to a network or another computer system (not shown) via a network interface 560, which will not be described in detail herein.
In the embodiment, the data instructions are stored in the memory, and then the instructions are processed by the processor, so that the calculation amount can be obviously reduced on the premise of basically ensuring the recommendation accuracy, and the calculation efficiency and the practical effect are greatly improved.
In another embodiment, the present disclosure also provides a computer-readable storage medium having stored thereon computer program instructions, which when executed by a processor, implement the steps of the method in the corresponding embodiment of fig. 1 and/or fig. 2. As will be appreciated by one skilled in the art, embodiments of the present disclosure may be provided as a method, apparatus, or computer program product. Accordingly, the present disclosure may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present disclosure may take the form of a computer program product embodied on one or more computer-usable non-transitory storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present disclosure is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Thus far, the present disclosure has been described in detail. Some details that are well known in the art have not been described in order to avoid obscuring the concepts of the present disclosure. It will be fully apparent to those skilled in the art from the foregoing description how to practice the presently disclosed embodiments.
The method and system of the present disclosure may be implemented in a number of ways. For example, the methods and systems of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise.
Although some specific embodiments of the present disclosure have been described in detail by way of example, it should be understood by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the present disclosure. It will be appreciated by those skilled in the art that modifications can be made to the above embodiments without departing from the scope and spirit of the present disclosure. The scope of the present disclosure is defined by the appended claims.
Claims (14)
1. A method for recommending communication services to a user, comprising:
determining each dimension of the communication service based on the existing communication service of the user;
performing box separation processing on each dimension, and distributing the users to corresponding feature groups according to box separation results;
searching a similar group of the user based on the box separation result, calculating to obtain a communication service structure proportion of the similar group, and taking the communication service structure proportion as a recommendation probability; and
selecting the communication service structure with the highest recommendation probability as a recommendation result from all communication service structures to be recommended to the user, and recommending the communication service to the user;
wherein, the step of calculating the communication service structure proportion of the similar group comprises: under the condition that the user currently has a plurality of communication services, calculating the proportion of the communication service structures in the corresponding similar groups according to each communication service; weighting the proportion of the same type of communication service structure in all similar groups, and calculating to obtain the weighted proportion of the communication service structure as the recommendation probability of the communication service structure;
the step of finding similar groups of the users based on the binning results comprises: searching and obtaining other users which are consistent with the box separation results of the users in all dimensions, and taking all the other users as similar groups of the users; wherein the similar groups are assigned to respective feature groups of the users;
before calculating the communication service structure proportion, the method further comprises the following steps: and judging whether the number of all users in the feature group is greater than or equal to a user number threshold value, if so, determining the feature group as an effective feature group, executing the step of calculating the communication service structure proportion, otherwise, determining the feature group as an ineffective feature group, and deleting the ineffective feature group.
2. The method of claim 1, wherein the step of performing binning on the dimensions and assigning the users to corresponding feature groups according to binning results comprises:
respectively allocating the users to corresponding box groups of all dimensions according to the data information of the users on all dimensions; and
assigning the user into a respective feature group according to the features of the respective group of bins for each dimension to which the user is assigned.
3. The method of claim 1, wherein the step of calculating the traffic structure proportion of the similar group comprises:
and respectively calculating the proportion of the number of the users having each communication service structure in the similar group to the total number of the users of the similar group, and taking the proportion as the communication service structure proportion of the similar group.
4. The method of claim 1, wherein,
the method further comprises the following steps: setting a recommendation threshold according to a recommendation service requirement;
the step of selecting the communication service structure with the highest recommendation probability as the recommendation result and recommending the communication service to the user comprises the following steps:
and taking the communication service structure to be recommended with the recommendation probability greater than the recommendation threshold as a product package, comparing the product package with the existing communication services of the user, and selecting the communication service structure with the highest recommendation probability from the product package to recommend the communication services which are not available to the user currently to the user.
5. The method of claim 1, wherein,
the communication service comprises: mobile service, broadband service or fixed line service;
the communication service structure comprises: single mobile service, single broadband service, single fixed telephone service, combined mobile and broadband service, combined mobile and fixed telephone service, combined broadband and fixed telephone service, or combined mobile, broadband and fixed telephone service.
6. The method of claim 5, wherein,
the dimensions of the mobile service include: at least one of call duration, General Packet Radio Service (GPRS) traffic, short messenger usage, circle of communication size, network access duration, equipment all-source income, quantity of mobile assets under the name of the user and quantity of postpaid assets under the name of the user;
the dimensions of the broadband service include: at least one of total internet access times, the number of internet access terminals, downlink bandwidth, internet access time, equipment full-source income, whether post-payment exists or not and whether a sales strategy exists or not;
the dimension of the fixed telephone service comprises: at least one of fixed-line calling duration, outgoing communication circle size, incoming communication circle size, network access duration and equipment full-source income.
7. A system for recommending communication services to a user, comprising:
the dimension acquisition unit is used for determining each dimension of the communication service based on the existing communication service of the user;
the box separation processing unit is used for respectively carrying out box separation processing on each dimension and distributing the users to corresponding feature groups according to box separation results;
the searching and calculating unit is used for searching a similar group of the user based on the box dividing result, calculating the communication service structure proportion of the similar group, and taking the communication service structure proportion as a recommendation probability; and
the service recommendation unit is used for selecting the communication service structure with the highest recommendation probability as a recommendation result from all communication service structures to be recommended to the user and recommending the communication service to the user;
the searching and calculating unit is used for calculating the proportion of the communication service structures in the corresponding similar groups according to each communication service under the condition that the user currently has a plurality of communication services, carrying out weighting processing on the proportion of the same type of communication service structures in all the similar groups, and calculating the weighting proportion of the type of communication service structure to be used as the recommendation probability of the type of communication service structure;
the searching and calculating unit is used for searching and obtaining all other users which are consistent with the user in the classification result of each dimension, and taking all the other users as the similar group of the users; wherein the similar groups are assigned to respective feature groups of the users; the searching and calculating unit is further configured to determine whether the number of all users in the feature group is greater than or equal to a user number threshold, if so, determine that the feature group is an effective feature group, calculate the communication service structure ratio, otherwise, determine that the feature group is an ineffective feature group, and delete the ineffective feature group.
8. The system of claim 7, wherein,
the box-dividing processing unit is used for respectively allocating the user to the corresponding box groups of the dimensions according to the data information of the user on the dimensions, and allocating the user to the corresponding characteristic groups according to the characteristics of the corresponding box groups of the dimensions to which the user is allocated.
9. The system of claim 7, wherein,
the searching and calculating unit is used for respectively calculating and obtaining the proportion of the number of the users having each communication service structure in the similar group to the total number of the users of the similar group as the communication service structure proportion of the similar group.
10. The system of claim 7, wherein,
the service recommending unit is used for setting a recommending threshold value according to recommending service requirements, taking a communication service structure to be recommended with a recommending probability larger than the recommending threshold value as a product package, comparing the product package with the existing communication services of the user, and selecting the communication service structure with the highest recommending probability from the product package to recommend the communication services which are not available at present of the user to the user.
11. The system of claim 7, wherein,
the communication service comprises: mobile service, broadband service or fixed line service;
the communication service structure comprises: single mobile service, single broadband service, single fixed telephone service, combined mobile and broadband service, combined mobile and fixed telephone service, combined broadband and fixed telephone service, or combined mobile, broadband and fixed telephone service.
12. The system of claim 11, wherein,
the dimensions of the mobile service include: at least one of call duration, General Packet Radio Service (GPRS) traffic, short messenger usage, circle of communication size, network access duration, equipment all-source income, quantity of mobile assets under the name of the user and quantity of postpaid assets under the name of the user;
the dimensions of the broadband service include: at least one of total internet access times, the number of internet access terminals, downlink bandwidth, internet access time, equipment full-source income, whether post-payment exists or not and whether a sales strategy exists or not;
the dimension of the fixed telephone service comprises: at least one of fixed-line calling duration, outgoing communication circle size, incoming communication circle size, network access duration and equipment full-source income.
13. A system for recommending communication services to a user, comprising:
a memory; and
a processor coupled to the memory, the processor configured to perform the method of any of claims 1-6 based on instructions stored in the memory.
14. A computer-readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the steps of the method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711428807.5A CN109962956B (en) | 2017-12-26 | 2017-12-26 | Method and system for recommending communication services to a user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711428807.5A CN109962956B (en) | 2017-12-26 | 2017-12-26 | Method and system for recommending communication services to a user |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109962956A CN109962956A (en) | 2019-07-02 |
| CN109962956B true CN109962956B (en) | 2022-06-07 |
Family
ID=67021760
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711428807.5A Active CN109962956B (en) | 2017-12-26 | 2017-12-26 | Method and system for recommending communication services to a user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109962956B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113409106B (en) * | 2021-06-04 | 2023-10-27 | 广州三七极创网络科技有限公司 | Commodity recommendation method, device, equipment and storage medium based on user value |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101465809A (en) * | 2009-01-16 | 2009-06-24 | 中国人民解放军信息工程大学 | Method, equipment and system for managing network flux |
| CN101882146A (en) * | 2010-05-18 | 2010-11-10 | 北京邮电大学 | A Clustering-Based Identification Method for Mobile Communication Service User False Opening |
| CN102045748A (en) * | 2010-12-16 | 2011-05-04 | 北京拓明科技有限公司 | Mobile network intelligent analysis method based on data service flow and system thereof |
| CN103714139A (en) * | 2013-12-20 | 2014-04-09 | 华南理工大学 | Parallel data mining method for identifying a mass of mobile client bases |
| CN104462320A (en) * | 2014-12-01 | 2015-03-25 | 中国联合网络通信集团有限公司 | Method and device for realizing classification of network users |
| CN106204083A (en) * | 2015-04-30 | 2016-12-07 | 中国移动通信集团山东有限公司 | A kind of targeted customer's sorting technique, Apparatus and system |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103905971B (en) * | 2014-03-26 | 2017-12-15 | 华为技术有限公司 | A kind of method and device for recommending traffic set meal |
| CN105281925B (en) * | 2014-06-30 | 2019-05-14 | 腾讯科技（深圳）有限公司 | The method and apparatus that network service groups of users divides |
| CN106991598A (en) * | 2017-04-07 | 2017-07-28 | 北京百分点信息科技有限公司 | Data push method and its system |
-
2017
- 2017-12-26 CN CN201711428807.5A patent/CN109962956B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101465809A (en) * | 2009-01-16 | 2009-06-24 | 中国人民解放军信息工程大学 | Method, equipment and system for managing network flux |
| CN101882146A (en) * | 2010-05-18 | 2010-11-10 | 北京邮电大学 | A Clustering-Based Identification Method for Mobile Communication Service User False Opening |
| CN102045748A (en) * | 2010-12-16 | 2011-05-04 | 北京拓明科技有限公司 | Mobile network intelligent analysis method based on data service flow and system thereof |
| CN103714139A (en) * | 2013-12-20 | 2014-04-09 | 华南理工大学 | Parallel data mining method for identifying a mass of mobile client bases |
| CN104462320A (en) * | 2014-12-01 | 2015-03-25 | 中国联合网络通信集团有限公司 | Method and device for realizing classification of network users |
| CN106204083A (en) * | 2015-04-30 | 2016-12-07 | 中国移动通信集团山东有限公司 | A kind of targeted customer's sorting technique, Apparatus and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109962956A (en) | 2019-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107526807B (en) | Information recommendation method and device | |
| CN106294508B (en) | Brushing amount tool detection method and device | |
| CN105005582A (en) | Recommendation method and device for multimedia information | |
| CN106790552B (en) | A kind of content providing system based on content distributing network | |
| KR20180017085A (en) | Location information providing method and device | |
| CN107896153B (en) | A method and device for recommending a data package based on the online behavior of a mobile user | |
| CN111506485A (en) | Feature binning method, apparatus, device, and computer-readable storage medium | |
| CN111541628A (en) | Power communication network service resource allocation method and related device | |
| Yu et al. | A coupled clustering approach for items recommendation | |
| CN110087228A (en) | A kind of determination method and device of service package | |
| CN109934675A (en) | Package recommendation method, device and system for new network users | |
| CN109962956B (en) | Method and system for recommending communication services to a user | |
| CN105681287A (en) | Screening rule based user service allocation screening method | |
| CN112861963A (en) | Method, device and storage medium for training entity feature extraction model | |
| CN108076032B (en) | Abnormal behavior user identification method and device | |
| CN110677269B (en) | Method and device for determining communication user relationship and computer readable storage medium | |
| US9794137B2 (en) | Method and apparatus for assigning network resource | |
| CN109213937B (en) | Intelligent search method and device | |
| CN104182546A (en) | Method and device for querying data in databases | |
| CN107659982B (en) | Wireless network access point classification method and device | |
| CN105704173B (en) | A kind of cluster system data distribution method and server | |
| CN107294734B (en) | Method, mobile terminal and system for switching internet access mode according to residual traffic | |
| CN113517990B (en) | A method and device for predicting network net promoter score NPS | |
| CN115797053A (en) | Fund lending routing method, storage medium and electronic equipment | |
| CN113392130B (en) | Data processing method, device and equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |